Object Detection in Real Images

TL;DR

This paper introduces a novel object detection and recognition method that leverages geometric cues, hierarchical codebooks, and a new learning approach to improve robustness, efficiency, and adaptability in real images.

Contribution

It proposes a comprehensive object detection framework incorporating geometric features, a hierarchical codebook, and an innovative learning method capable of online and generative-discriminative training.

Findings

Preliminary work on detecting geometric shapes in real images completed.

The hierarchical codebook enables fast, robust multi-path inference.

The new learning method supports online and less supervised training.

Abstract

Object detection and recognition are important problems in computer vision. Since these problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real-time, and dynamic object detection/recognition methods are still unavailable. We propose a new object detection/recognition method, which improves over the existing methods in every stage of the object detection/recognition process. In addition to the usual features, we propose to use geometric shapes, like linear cues, ellipses and quadrangles, as additional features. The full potential of geometric cues is exploited by using them to extract other features in a robust, computationally efficient, and less meta-heuristic manner. We also propose a new hierarchical codebook, which provides good generalization and discriminative properties. The codebook enables fast multi-path inference mechanisms based on propagation of conditional likelihoods, that make it robust to occlusion and noise. It has the capability of dynamic learning. We also propose a new learning method that has generative and discriminative learning capabilities, does not need large and fully supervised training dataset, and is capable of online learning. The preliminary work of detecting geometric shapes in real images has been completed. This preliminary work is the focus of this report. Future path for realizing the proposed object detection/recognition method is also discussed in brief.